Kitware Works with NVIDIA to Drive Massive Acceleration in HPC Visualization
Kitware, Inc., today announced it is working with NVIDIA to develop several powerful enhancements for the field of high performance computing (HPC) visualization.
Among these is a new Visualization Toolkit (VTK) rendering backend, which targets graphics processing units (GPUs) and takes advantage of the flexible programmable pipelines available in modern systems. This development has already resulted in significant improvements in rendering performance, especially with large geometries (20 million+ triangles) that can now be rendered over 100 times faster.
“Through our collaboration with NVIDIA, we will enhance the open-source VTK and ParaView to better serve the HPC visualization community,” said Dr. Berk Geveci, Kitware’s Senior Director of Scientific Computing.
In addition, as part of the Department of Energy (DOE) Advanced Scientific Computing Research (ASCR) project “XVis: Visualization for the Extreme-Scale Scientific-Computation Ecosystem,” Kitware, in collaboration with government labs and academia, is developing a unified visualization library, named VTK-m, as a single point to collaborate, contribute, and leverage massively threaded visualization algorithms. Kitware will be demonstrating VTK-m in NVIDIA GPU-accelerated applications in in situ mode within ParaView Catalyst.
NVIDIA will add future EGL support to its drivers, eliminating the need to install an X server for graphics output in ParaView. The companies are also exploring bringing OptiX parallel ray tracing and volume visualization capabilities into ParaView for better insight into simulations.
This collaboration will enable VTK and ParaView to fully benefit from the huge computational and graphics performance NVIDIA Tesla and Quadro architectures provide.
To learn more about Kitware’s HPC and visualization expertise and how it can be used to your organization’s advantage, please visit Kitware at booth 1354 at SC14 in New Orleans, LA, where the company will be demonstrating its work in HPC. In addition, Robert Maynard will present a GPU technology theater talk, “VTK-M: Uniting GPU acceleration successes in large-scale HPC visualization,” at the conference on November 19, 2014, at 3:00 pm. Kitware can also be reached through email at kitware(at)kitware(dot)com.
This material is based upon work supported by the U.S. Department of Energy, Office of Science, under Award Number DE-SC0012386.
Research reported in this publication was supported by the National Institute Of Biomedical Imaging And Bioengineering of the National Institutes of Health under Award Number R01EB014955. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.